Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Well beyond the annotations, the description discloses the payment profile (x402 exact USDC on Base / Scout credits, `payer` argument, x-tollbridge-payer header, PAYMENT-SIGNATURE), that unpaid calls return a payment_required challenge and never fabricated data, that refusals refund the debit, and that unknown/delisted symbols yield a typed 404. It adds genuine behavior the readOnlyHint/openWorldHint/idempotentHint trio does not cover; the one gap is that it never reconciles the paid, debit/refund nature with the declared readOnlyHint.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description opens with payment mechanics rather than purpose, then dumps a huge LIVE-set enumeration in which the same IDs repeat verbatim (X05 five times, X06 five times, X09 six times, S01 twice), inflating length without adding information. The genuinely useful parts (agent loop, refusal/refund semantics, payment rails) are scattered across the wall of text instead of front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return-value detail is not required, and the description covers payment, refunds, refusals, 404s, and the resolution-polling loop. However, for a tool with 5 parameters and a large question catalog, it leaves `question_version` undefined and the duplicated LIVE list makes it impossible to tell how many distinct askable questions exist, which an agent needs before invoking.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 20%, so the description has to carry the load and largely does: it explains that `asset` may be any symbol tollbridge_universe lists and that unknown symbols produce a typed 404, enumerates the askable `question_id` values and what each one queries (asset vs wallet, funding, OI, tape, etc.), and explains the `payer` alternatives and format. It never explains `question_version`, and the duplicated question list muddies the mapping.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The sentence 'Deep decision: ask a catalog signal through the decision engine for an asset on base — probability, confidence, policy verdict, horizons and ledger-grade provenance' gives a specific verb+resource and even names the outputs. It is clear, but the purpose is not front-loaded (the description opens with payment rail mechanics) and it never contrasts itself with near-siblings such as tollbridge_get_decision, tollbridge_get_resolution, or tollbridge_call, so sibling differentiation is left to inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives a concrete operating loop ('get latest → get resolution → if terminal and the question is available, ask the NEXT dated sentence') and states that blocked questions S02/S03/S04 return a typed out_of_scope refusal rather than a gradeless probability. That is actionable context, but it never says when to pick this tool over the other decision/query siblings, so there are no explicit alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.